Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies

• URL: http://arxiv.org/abs/2607.08270v1
• Date: Thu, 09 Jul 2026 09:13:03 GMT
• Title: Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies
• Abstract summary: Forecasting the future anatomy of slow-evolving neurodegenerative diseases could enable earlier, more targeted intervention and improve clinical trial design.<n>Latent Drift is a progressive generative framework that learns change in a compressed semantic representation rather than full-resolution anatomy.<n> Experiments on longitudinal 3D brain MRI show that Latent Drift improves patient-specific neuro-forecasting over diffusion and autoregressive transformer baselines.
• Score: 25.820056271749788
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Forecasting the future anatomy of slow-evolving neurodegenerative diseases could enable earlier, more targeted intervention and improve clinical trial design, but it remains challenging because true progression signals are subtle in longitudinal MRI. In this low-signal regime, transferring modern generative sequence models directly is unreliable: training is dominated by stable baseline anatomy and confounded by dense, sample-specific nuisance variation. We first provide a theoretical analysis that explains these failures through two modes. Identity collapse occurs when optimization is driven toward reproducing the current anatomy, which prevents the model from learning faint temporal change. The continuous interpolation trap arises when standard smooth networks cannot separate localized biological drift from pervasive noise, which leads to spurious changes that diffuse across the volume. To address both issues, we propose Latent Drift, a progressive generative framework that learns change in a compressed semantic representation rather than synthesizing full-resolution anatomy. This design removes pixel-level identity from the prediction target and concentrates model capacity on progression-relevant dynamics. We further apply Finite Scalar Quantization to the learned change representation, which suppresses small, high-frequency nuisance fluctuations while preserving consistent structural drift. Experiments on longitudinal 3D brain MRI show that Latent Drift improves patient-specific neuro-forecasting over diffusion and autoregressive transformer baselines across generative fidelity and clinically relevant evaluation metrics. Project page: \href{https://cutepkq.github.io/latent-drift}{https://cutepkq.github.io/latent-drift}.

Related papers

• ProgFormer: Hierarchical Voxel Diffusion Transformer for Longitudinal Brain MRI Prediction [81.07048249760953]
  longitudinal changes are often subtle and confined to specific anatomical regions.<n>Most subject-specific brain structure remains stable over time.<n>ProgFormer is a hierarchical voxel-space Diffusion Transformer for longitudinal brain MRI prediction.
  arXiv  Detail & Related papers  (2026-07-30T00:13:42Z)
• Generative Modeling of Neurodegenerative Brain Anatomy with 4D Longitudinal Diffusion Model [4.65021411381981]
  Most longitudinal neuroimaging datasets are temporally sparse with a few follow-up scans per subject.<n>We propose a novel 4D (3DxT) diffusion-based generative framework that effectively models and synthesizes longitudinal anatomy over time.<n>Our method outperforms state-of-the-art baselines in generating anatomically accurate, temporally consistent, and clinically meaningful brain trajectories.
  arXiv  Detail & Related papers  (2026-04-24T16:33:48Z)
• SDE-Driven Spatio-Temporal Hypergraph Neural Networks for Irregular Longitudinal fMRI Connectome Modeling in Alzheimer's Disease [18.4869028609927]
  We propose a graph-anonymous differential equation (SDE)-driven hypertemporal neural network for irregular longitudinal fMRI connectome modeling.<n>The framework first employs an SDE-based reconstruction module to recover continuous latent trajectories from irregular observations.<n>To further model temporal evolution, hypergraph parameters evolve through SDE-controlled neuroimaging dynamics conditioned on inter-scan intervals.
  arXiv  Detail & Related papers  (2026-03-20T19:31:05Z)
• Unleashing Temporal Capacity of Spiking Neural Networks through Spatiotemporal Separation [67.69345363409835]
  Spiking Neural Networks (SNNs) are considered naturally suited for temporal processing, with membrane potential propagation widely regarded as the core temporal modeling mechanism.<n>We design Non-Stateful (NS) models progressively removing membrane propagation to its stage-wise role. Experiments reveal a counterintuitive phenomenon: moderate removal in shallow layers improves performance, while excessive removal causes collapse.
  arXiv  Detail & Related papers  (2025-12-05T07:05:53Z)
• Stable-Drift: A Patient-Aware Latent Drift Replay Method for Stabilizing Representations in Continual Learning [3.1965482926781843]
  When deep learning models are sequentially trained on new data, they tend to abruptly lose performance on previously learned tasks.<n>We introduce a latent drift-guided replay method that identifies and replays samples with high representational instability.<n>Our method substantially reduces forgetting compared to naive fine-tuning and random replay.
  arXiv  Detail & Related papers  (2025-11-27T16:49:50Z)
• Conditional Neural ODE for Longitudinal Parkinson's Disease Progression Forecasting [51.906871559732245]
  Parkinson's disease (PD) shows heterogeneous, evolving brain-morphometry patterns.<n>Modeling these longitudinal trajectories enables mechanistic insight, treatment development, and individualized 'digital-twin' forecasting.<n>We propose CNODE, a novel framework for continuous, individualized PD progression forecasting.
  arXiv  Detail & Related papers  (2025-11-06T20:16:33Z)
• Langevin Flows for Modeling Neural Latent Dynamics [81.81271685018284]
  We introduce LangevinFlow, a sequential Variational Auto-Encoder where the time evolution of latent variables is governed by the underdamped Langevin equation.<n>Our approach incorporates physical priors -- such as inertia, damping, a learned potential function, and forces -- to represent both autonomous and non-autonomous processes in neural systems.<n>Our method outperforms state-of-the-art baselines on synthetic neural populations generated by a Lorenz attractor.
  arXiv  Detail & Related papers  (2025-07-15T17:57:48Z)
• New Evidence of the Two-Phase Learning Dynamics of Neural Networks [59.55028392232715]
  We introduce an interval-wise perspective that compares network states across a time window.<n>We show that the response of the network to a perturbation exhibits a transition from chaotic to stable.<n>We also find that after this transition point the model's functional trajectory is confined to a narrow cone-shaped subset.
  arXiv  Detail & Related papers  (2025-05-20T04:03:52Z)
• One-for-More: Continual Diffusion Model for Anomaly Detection [63.50488826645681]
  Anomaly detection methods utilize diffusion models to generate or reconstruct normal samples when given arbitrary anomaly images.<n>Our study found that the diffusion model suffers from severe faithfulness hallucination'' and catastrophic forgetting''<n>We propose a continual diffusion model that uses gradient projection to achieve stable continual learning.
  arXiv  Detail & Related papers  (2025-02-27T07:47:27Z)
• Stochastic Gradient Descent-Induced Drift of Representation in a Two-Layer Neural Network [0.0]
  Despite being observed in the brain and in artificial networks, the mechanisms of drift and its implications are not fully understood. Motivated by recent experimental findings of stimulus-dependent drift in the piriform cortex, we use theory and simulations to study this phenomenon in a two-layer linear feedforward network.
  arXiv  Detail & Related papers  (2023-02-06T04:56:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.